Structural connectome validation using pairwise classification

Dmitry Petrov; Boris Gutman; Alexander Ivanov; Joshua Faskowitz; Neda Jahanshad; Mikhail Belyaev; Paul Thompson

doi:10.1109/ISBI.2017.7950558

Structural connectome validation using pairwise classification

Dmitry Petrov, Boris Gutman, Alexander Ivanov, Joshua Faskowitz, Neda Jahanshad, Mikhail Belyaev, Paul Thompson

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this work, we study the extent to which structural connectomes and topological derivative measures are unique to individual changes within human brains. To do so, we classify structural connectome pairs from two large longitudinal datasets as either belonging to the same individual or not. Our data is comprised of 227 individuals from the Alzheimers Disease Neuroimaging Initiative (ADNI) and 226 from the Parkinson's Progression Markers Initiative (PPMI). We achieve 0.99 area under the ROC curve score for features which represent either weights or network structure of the connectomes (node degrees, PageRank and local efficiency). Our approach may be useful for eliminating noisy features as a preprocessing step in brain aging studies and early diagnosis classification problems.

Original language	English
Title of host publication	2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017
Publisher	IEEE Computer Society
Pages	451-455
Number of pages	5
ISBN (Electronic)	9781509011711
DOIs	https://doi.org/10.1109/ISBI.2017.7950558
State	Published - 15 Jun 2017
Externally published	Yes
Event	14th IEEE International Symposium on Biomedical Imaging, ISBI 2017 - Melbourne, Australia Duration: 18 Apr 2017 → 21 Apr 2017

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	14th IEEE International Symposium on Biomedical Imaging, ISBI 2017
Country/Territory	Australia
City	Melbourne
Period	18/04/17 → 21/04/17

Keywords

DWI
Machine learning
Structural connectomes

Access to Document

10.1109/ISBI.2017.7950558

Cite this

Petrov, D., Gutman, B., Ivanov, A., Faskowitz, J., Jahanshad, N., Belyaev, M., & Thompson, P. (2017). Structural connectome validation using pairwise classification. In 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017 (pp. 451-455). Article 7950558 (Proceedings - International Symposium on Biomedical Imaging). IEEE Computer Society. https://doi.org/10.1109/ISBI.2017.7950558

@inproceedings{0e55c4e39a404c0fb191c0c2e195e041,

title = "Structural connectome validation using pairwise classification",

abstract = "In this work, we study the extent to which structural connectomes and topological derivative measures are unique to individual changes within human brains. To do so, we classify structural connectome pairs from two large longitudinal datasets as either belonging to the same individual or not. Our data is comprised of 227 individuals from the Alzheimers Disease Neuroimaging Initiative (ADNI) and 226 from the Parkinson's Progression Markers Initiative (PPMI). We achieve 0.99 area under the ROC curve score for features which represent either weights or network structure of the connectomes (node degrees, PageRank and local efficiency). Our approach may be useful for eliminating noisy features as a preprocessing step in brain aging studies and early diagnosis classification problems.",

keywords = "DWI, Machine learning, Structural connectomes",

author = "Dmitry Petrov and Boris Gutman and Alexander Ivanov and Joshua Faskowitz and Neda Jahanshad and Mikhail Belyaev and Paul Thompson",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 14th IEEE International Symposium on Biomedical Imaging, ISBI 2017 ; Conference date: 18-04-2017 Through 21-04-2017",

year = "2017",

month = jun,

day = "15",

doi = "10.1109/ISBI.2017.7950558",

language = "English",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

pages = "451--455",

booktitle = "2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017",

address = "United States",

}

Petrov, D, Gutman, B, Ivanov, A, Faskowitz, J, Jahanshad, N, Belyaev, M & Thompson, P 2017, Structural connectome validation using pairwise classification. in 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017., 7950558, Proceedings - International Symposium on Biomedical Imaging, IEEE Computer Society, pp. 451-455, 14th IEEE International Symposium on Biomedical Imaging, ISBI 2017, Melbourne, Australia, 18/04/17. https://doi.org/10.1109/ISBI.2017.7950558

Structural connectome validation using pairwise classification. / Petrov, Dmitry; Gutman, Boris; Ivanov, Alexander et al.
2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017. IEEE Computer Society, 2017. p. 451-455 7950558 (Proceedings - International Symposium on Biomedical Imaging).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Structural connectome validation using pairwise classification

AU - Petrov, Dmitry

AU - Gutman, Boris

AU - Ivanov, Alexander

AU - Faskowitz, Joshua

AU - Jahanshad, Neda

AU - Belyaev, Mikhail

AU - Thompson, Paul

PY - 2017/6/15

Y1 - 2017/6/15

N2 - In this work, we study the extent to which structural connectomes and topological derivative measures are unique to individual changes within human brains. To do so, we classify structural connectome pairs from two large longitudinal datasets as either belonging to the same individual or not. Our data is comprised of 227 individuals from the Alzheimers Disease Neuroimaging Initiative (ADNI) and 226 from the Parkinson's Progression Markers Initiative (PPMI). We achieve 0.99 area under the ROC curve score for features which represent either weights or network structure of the connectomes (node degrees, PageRank and local efficiency). Our approach may be useful for eliminating noisy features as a preprocessing step in brain aging studies and early diagnosis classification problems.

AB - In this work, we study the extent to which structural connectomes and topological derivative measures are unique to individual changes within human brains. To do so, we classify structural connectome pairs from two large longitudinal datasets as either belonging to the same individual or not. Our data is comprised of 227 individuals from the Alzheimers Disease Neuroimaging Initiative (ADNI) and 226 from the Parkinson's Progression Markers Initiative (PPMI). We achieve 0.99 area under the ROC curve score for features which represent either weights or network structure of the connectomes (node degrees, PageRank and local efficiency). Our approach may be useful for eliminating noisy features as a preprocessing step in brain aging studies and early diagnosis classification problems.

KW - DWI

KW - Machine learning

KW - Structural connectomes

UR - http://www.scopus.com/inward/record.url?scp=85023179183&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2017.7950558

DO - 10.1109/ISBI.2017.7950558

M3 - Conference contribution

AN - SCOPUS:85023179183

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 451

EP - 455

BT - 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017

PB - IEEE Computer Society

T2 - 14th IEEE International Symposium on Biomedical Imaging, ISBI 2017

Y2 - 18 April 2017 through 21 April 2017

ER -

Structural connectome validation using pairwise classification

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this